慢性阻塞性肺疾病患者急性肾脏疾病及不良结局风险预测：一种可解释的机器学习方法
基于2829名COPD患者临床数据，使用机器学习预测急性肾损伤、急性肾脏疾病及死亡风险的表格数据集。
基本信息
资源简介
慢性阻塞性肺疾病患者急性肾脏疾病及不良结局风险预测：一种可解释的机器学习方法
【一句话概览】
本数据集是 figshare 公开的结构化表格数据集，收录 2 个文件、合计 7.53 MB，主题涵盖 Acute kidney disease、acute kidney injury、chronic obstructive pulmonary disease、machine learning、mortality，可用于统计建模、特征工程与队列分析，CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach》。配套论文《Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach》发表于 Renal Failure（2025），DOI：10.1080/0886022X.2025.2485475。项目资助方：This study was supported by the National Natural Science Foundation of China (grant numbers 81970582 and 82270724); the Taishan Scholar Program of Shandong Province (grant number tstp20230665); the Qingdao Key Health Discipline Development Fund; and the Qingdao Key Clinical Specialty Elite Discipline.。源站首次发布：2025-04-08。
【数据内容】
源站原始描述：Little is known about acute kidney injury (AKI) and acute kidney disease (AKD) in patients with chronic obstructive pulmonary disease (COPD) and COPD mortality based on the acute/subacute renal injury. This study develops machine learning models to predict AKI, AKD, and mortality in COPD patients, utilizing web applications for clinical decisions. We included 2,829 inpatients from January 2016 to December 2018. Data were split into 80% for training and 20% for testing. Eight machine learning alg…
中文译文（机器翻译，仅供快速理解，请以原文为准）：关于慢性阻塞性肺疾病（COPD）患者中急性肾损伤（AKI）和急性肾病（AKD）以及基于急性/亚急性肾损伤的COPD死亡率，目前所知甚少。本研究开发机器学习模型来预测COPD患者的AKI、AKD和死亡率，并利用网络应用程序辅助临床决策。 我们纳入了2016年1月至2018年12月期间的2，829例住院患者。数据按80%用于训练、20%用于测试进行划分。使用了八种机器学习算法，并采用多种指标评估模型性能。使用SHAP对决策过程进行可视化。根据AUROC评估出的最佳模型被用于开发网络应用程序，以识别高风险患者。 AKI的发生率为13.71%，AKD为15.11%。总体死亡率为4.84%。LightGBM表现最佳，在AKI、AKD和死亡率中的AUROC分别为0.815、0.827和0.934。AKI的关键预测因素为Scr、中性粒细胞百分比、胱抑素c、BUN和LDH。对于AKD，关键预测因素为年龄、AKI分级、HDL-C、Scr和BUN。死亡率的关键预测因素包括多巴胺和肾上腺素药物的使用、胱抑素c、肾功能轨迹、白蛋白和中性粒细胞百分比。Force plots可视化了个体患者的预测过程。 COPD患者中AKI和AKD的发生率较高。肾功能轨迹对于预测这些患者的死亡率至关重要。我们开发了用于预测AKI、AKD和死亡率的网络应用程序，通过识别高风险患者来改善预后，并减少不良事件和疾病进展。
【数据结构与技术规格】
文件数 2 个，合计 7.53 MB。irnf_a_2485475_sm1850.tif：image/tiff，2.99 MB。irnf_a_2485475_sm1848.tif：image/tiff，4.54 MB。数据集 DOI：10.6084/m9.figshare.28748338.v1。
【主题与分类】
源站学科分类：Biochemistry、Medicine、Microbiology、Immunology、Biological Sciences not elsewhere classified、Mathematical Sciences not elsewhere classified。主题标签：Acute kidney disease、acute kidney injury、chronic obstructive pulmonary disease、machine learning、mortality、predictive model。
【适用方向】
结构化表格数据可直接用于统计建模、特征工程与队列分析。
【获取与许可】
源站页面：https://tandf.figshare.com/articles/dataset/Risk_prediction_for_acute_kidney_disease_and_adverse_outcomes_in_patients_with_chronic_obstructive_pulmonary_disease_an_interpretable_machine_learning_approach/28748338
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach. Taylor & Francis. Jiang, Siqi; Xu, Lingyu; Wang, Xinyuan; Li, Chenyu; Guan, Chen; Che, Lin; et al
【使用注意】
· 源站最后修改于 2026-09-28，引用时请注意版本时效。
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取（Figshare）
- 源站标题：Risk prediction for acute kidney disease and adverse outcomes in patients with chronic obstructive pulmonary disease: an interpretable machine learning approach
- DOI：10.6084/m9.figshare.28748338.v1
- 发布日期：2025-04-08
- 文件数：2 个
- 文件总体积：7.53 MB
- 源站页面：https://tandf.figshare.com/articles/dataset/Risk_prediction_for_acute_kidney_disease_and_adverse_outcomes_in_patients_with_chronic_obstructive_pulmonary_disease_an_interpretable_machine_learning_approach/28748338
命令行下载
curl -L -o "irnf_a_2485475_sm1850.tif" "https://ndownloader.figshare.com/files/53489095"
curl -L -o "irnf_a_2485475_sm1848.tif" "https://ndownloader.figshare.com/files/53489098"
文件清单
irnf_a_2485475_sm1850.tif（2.99 MB）irnf_a_2485475_sm1848.tif（4.54 MB）
文件总体积 7.53 MB（源站 API 实测）。
数据加载示例（图像类）
from PIL import Image
import glob, os
files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
+ glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)
# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path) # 要求 子目录=类别
目录组织与标注格式以源站说明和下载后实际文件为准。
数据说明
Little is known about acute kidney injury (AKI) and acute kidney disease (AKD) in patients with chronic obstructive pulmonary disease (COPD) and COPD mortality based on the acute/subacute renal injury. This study develops machine learning models to predict AKI, AKD, and mortality in COPD patients, utilizing web applications for clinical decisions.
We included 2,829 inpatients from January 2016 to December 2018. Data were split into 80% for training and 20% for testing. Eight machine learning algorithms were used, and model performance was evaluated using various metrics. SHAP was used to visualize the decision process. The best models, assessed using AUROC were used to develop web applications for identifying high-risk patients.
The incidence rates were 13.71% for AKI and 15.11% for AKD. The overall mortality rate was 4.84%. LightGBM performed best with AUROC of 0.815, 0.827, and 0.934 in AKI, AKD, and mortality, respectively. Key predictors for AKI were Scr, neutrophil percentage, cystatin c, BUN, and LDH. For AKD, the key predictors were age, AKI grade, HDL-C, Scr, and BUN. The key predictors for mortality included the use of dopamine and epinephrine drugs, cystatin c, renal function trajectory, albumin, and neutrophil percentage. Force plots visualized the prediction process for individual patients.
The incidence of AKI and AKD is significant in patients with COPD. Renal function trajectory is crucial for predicting mortality in these patients. Web applications were developed to predict AKI, AKD, and mortality, improving prognosis by identifying high-risk patients and reducing adverse events and disease progression.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.28748338.v1（source: https://tandf.figshare.com/articles/dataset/Risk_prediction_for_acute_kidney_disease_and_adverse_outcomes_in_patients_with_chronic_obstructive_pulmonary_disease_an_interpretable_machine_learning_approach/28748338）。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
